v1

latestOpenAPI 3.1.02026-07-1381127211.1 KB
Video Emotion API

Trigger Personality Analysis

Trigger personality analysis for a specific face in a video.

Initiates asynchronous personality trait assessment based on facial expressions and, when available, vocal characteristics from linked audio speaker data.

Analysis Types

  • overall: Analyzes personality traits across the entire video
  • by_segment: Analyzes personality traits by time segments
  • combined: Performs both overall and segment analysis

Overall and segment analyses are independent - triggering one does not affect the other.

Multimodal Analysis

  • Face only: Analyzes facial expressions when no speaker is linked
  • Face + Audio: Combines facial and vocal characteristics when face is linked to a speaker

Prerequisites

  • Video must be completed
  • Face ID must exist in the video
  • If face has speaker mapping: audio must be completed
  • User must have sufficient credits

Request

{
  "face_id": 1,
  "analysis_type": "overall",
  "callback_url": "https://example.com/webhook"
}

Response

{
  "video_id": "abc123",
  "face_id": 1,
  "speaker_id": 2,
  "analysis_type": "overall",
  "status": "processing",
  "message": "Personality analysis triggered successfully"
}

Credit Usage

Credits are billed per minute of video duration based on analysis_type.

analysis_typePersonalProfessional & Enterprise
overall30 credits/min15 credits/min
by_segment50 credits/min25 credits/min
combined60 credits/min30 credits/min

Notes

  • Analysis runs asynchronously in the background
  • Use callback_url for webhook notifications when complete
  • Credits are deducted when analysis is triggered
  • Retrieve results using the video analytics endpoints
post/v2/videos/{video_id}/personality/analyze

Path parameters

video_idstring required

Unique identifier of the video. Video must be in 'completed' status with detected faces.

Unique identifier of the video. Video must be in 'completed' status with detected faces.

Response

Successful Response

video_idstring required
face_idinteger required
speaker_idinteger nullable
analysis_typestring required
statusstring required
messagestring required